dixedus commited on
Commit
be15a19
·
verified ·
1 Parent(s): 1c512fd

Training in progress, step 27, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ba20da035b1270eb67739c24babe540d441fc2e4984058f1b42898a2b203028
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dde04550207fe998575bbf756e49b0da5a93e295e628f1163c408d2c776149eb
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbc9082c87d2fd4bb0ba42ada39e023c3f90444bb05eeaa6f261fc1f9646f040
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d9793917551a2bf8e7c8ac69dab0bc0d779e7a867bcbd87b4fd39d74fde5fc4
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cf30c4e1dfd3b199f004d48c615f0058d9d8168fc7715316fa0d2b53a3286f2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b4f63aec6d8b3291c19fe2b4497f750eeddd6b87b84886cefc94a6bfc39de55
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.47368421052631576,
5
  "eval_steps": 9,
6
- "global_step": 18,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 14.244,
74
  "eval_steps_per_second": 1.78,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 2.531269094355763e+16,
96
  "train_batch_size": 8,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.7105263157894737,
5
  "eval_steps": 9,
6
+ "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 14.244,
74
  "eval_steps_per_second": 1.78,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.5526315789473685,
79
+ "grad_norm": 8.11834716796875,
80
+ "learning_rate": 9.635919272833938e-05,
81
+ "loss": 3.2265,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.631578947368421,
86
+ "grad_norm": 10.354762077331543,
87
+ "learning_rate": 9.414737964294636e-05,
88
+ "loss": 3.3718,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.7105263157894737,
93
+ "grad_norm": 8.096390724182129,
94
+ "learning_rate": 9.145187862775209e-05,
95
+ "loss": 3.5513,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.7105263157894737,
100
+ "eval_loss": 0.8040823340415955,
101
+ "eval_runtime": 4.4907,
102
+ "eval_samples_per_second": 14.252,
103
+ "eval_steps_per_second": 1.781,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 3.796903641533645e+16,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null